Current UAV-recorded datasets are mostly limited to action recognition and object tracking, whereas the gesture signals datasets were mostly recorded in indoor spaces. Currently, there is no outdoor recorded public video dataset for UAV commanding signals. Gesture signals can be effectively used with UAVs by leveraging the UAVs visual sensors and operational simplicity. To fill this gap and enable research in wider application areas, we present a UAV gesture signals dataset recorded in an outdoor setting. We selected 13 gestures suitable for basic UAV navigation and command from general aircraft handling and helicopter handling signals. We provide 119 high-definition video clips consisting of 37151 frames. The overall baseline gesture recognition performance computed using Pose-based Convolutional Neural Network (P-CNN) is 91.9 %. All the frames are annotated with body joints and gesture classes in order to extend the dataset's applicability to a wider research area including gesture recognition, action recognition, human pose recognition and situation awareness.

One noninvasive way to study frog communities is by analyzing long-term samples of acoustic material containing calls. This immense task has been optimized by the development of Machine Learning tools to extract ecological information. We explored a likelihood-ratio audio detector based on Gaussian mixture model classification of 10 frog species, and applied it to estimate presence-absence in audio recordings from an actual amphibian monitoring performed at Yasun ı National Park in the Ecuadorian Amazonia. A modified filter-bank was used to extract 20 cepstral features that model the spectral content of frog calls. Experiments were carried out to investigate the hyperparameters and the minimum frog-call time needed to train an accurate GMM classifier. With 64 Gaussians and 12 seconds of training time, the classifier achieved an average weighted error rate of 0.9% on the 10-fold cross-validation for nine species classification, as compared to 3% with MFCC and 1.8% with PLP features. For testing, 10 GMMs were trained using all the available training-validation dataset to study 23.5 hours in 141, 10-minute long samples of unidentified real-world audio recorded at two frog communities in 2001 with analog equipment. To evaluate automatic presence-absence estimation, we characterized the audio samples with 10 binary variables each corresponding to a frog species, and manually labeled a subset of 18 samples using headphones. The one-vs-all Receiver Operating Characteristics curves were used to tune the likelihood-ratio detector per class in order to set operating points that minimize false positives while still allowing moderately noisy calls to be detected. A recall of 87.5% and precision of 100% with average accuracy of 96.66% suggests good generalization ability of the algorithm, and provides evidence of the validity of this approach Finally, we applied the algorithm to the available corpus, and show its potentiality to gain insights into the temporal reproductive behavior of frogs. Introduction In long term ecological studies, it is important to quantify changes that occur on biodiversity and the ecosystem as a whole. Large scale temporal and spatial studies to understand the natural and anthropogenic induced population dynamics are demanded by the scientific community. In addition, recent anuran population declines around the world have motivated studies to gain an understanding of the phenomenon [1].

Abstract--Recently, a number of works have studied clustering strategies that combine classical clustering algorithms and deep learning methods. These approaches follow either a sequential way, where a deep representation is learned using a deep autoencoder before obtaining clusters with k-means, or a simultaneous way,where deep representation and clusters are learned jointly by optimizing a single objective function. Both strategies improve clustering performance, however the robustness of these approaches is impeded by several deep autoencoder setting issues, among which the weights initialization, the width and number of layers or the number of epochs. To alleviate the impact of such hyperparameters setting on the clustering performance, we propose a new model which combines the spectral clustering and deep autoencoder strengths in an ensemble learning framework. Extensive experiments on various benchmark datasets demonstrate thepotential and robustness of our approach compared to state-of-the art deep clustering methods. I. INTRODUCTION Learning from large amount of data is a very challenging task. Several dimensionality reduction and clustering techniques thatare well studied in the literature aim to learn a suitable and simplified data representation from original dataset; see for instance [1-3]. While many approaches have been proposed to address the dimensionality reduction and clustering tasks, deep learning-based methods recently demonstrate promisingresults.

Generative Adversarial Networks (GAN) boast impressive capacity to generate realistic images. However, like much of the field of deep learning, they require an inordinate amount of data to produce results, thereby limiting their usefulness in generating novelty. In the same vein, recent advances in meta-learning have opened the door to many few-shot learning applications. In the present work, we propose Few-shot Image Generation using Reptile (FIGR), a GAN meta-trained with Reptile. Our model successfully generates novel images on both MNIST and Omniglot with as little as 4 images from an unseen class. We further contribute FIGR-8, a new dataset for few-shot image generation, which contains 1,548,944 icons categorized in over 18,409 classes. Trained on FIGR-8, initial results show that our model can generalize to more advanced concepts (such as "bird" and "knife") from as few as 8 samples from a previously unseen class of images and as little as 10 training steps through those 8 images. This work demonstrates the potential of training a GAN for few-shot image generation and aims to set a new benchmark for future work in the domain.

Machine learning and cloud are set to continue as'hot topics' in 2019. As technology evolves, organisations that don't take the reins in terms of machine learning and cloud adoption may see themselves left behind. You only have to look as far as the Australian market to see numerous initiatives and great projects taking place. However, to be successful, they must have data at the centre of their attention. According to Gartner, machine learning promises to transform business processes; it will not only reconfigure the workforce, optimise infrastructure behaviour, but also blend industries through rapidly improved decision making and process optimisation.

CANBERRA: Five car manufacturers would have level three and four autonomous vehicles available by 2020, rising to 14 by 2022, the Australian National Transport Commission (NTC) said Monday, warning lawmakers must prepare for an autonomous vehicle boom. In a submission to the parliamentary infrastructure and transport committee, the NTC said that there could be between 740,000 and 1.7 million autonomous vehicles on Australian roads by 2020 and 9.5 million by 2030. Michael McCormack, Australia's Deputy Prime Minister (PM), said that the government was working with industry groups to prepare for the rapid rollout. "I want to ensure these new technologies are deployed in a manner which improves safety, productivity, accessibility and liveability for Australians in both urban and regional areas," he told News Corp Australia on Monday. Level three autonomous vehicles are vehicles that can drive themselves but require a driver capable of taking control at all times while level four vehicles can perform all driving functions autonomously with the option of driver control.

Accurate house prediction is of great significance to various real estate stakeholders such as house owners, buyers, investors, and agents. We propose a location-centered prediction framework that differs from existing work in terms of data profiling and prediction model. Regarding data profiling, we define and capture a fine-grained location profile powered by a diverse range of location data sources, such as transportation profile (e.g., distance to nearest train station), education profile (e.g., school zones and ranking), suburb profile based on census data, facility profile (e.g., nearby hospitals, supermarkets). Regarding the choice of prediction model, we observe that a variety of approaches either consider the entire house data for modeling, or split the entire data and model each partition independently. However, such modeling ignores the relatedness between partitions, and for all prediction scenarios, there may not be sufficient training samples per partition for the latter approach. We address this problem by conducting a careful study of exploiting the Multi-Task Learning (MTL) model. Specifically, we map the strategies for splitting the entire house data to the ways the tasks are defined in MTL, and each partition obtained is aligned with a task. Furthermore, we select specific MTL-based methods with different regularization terms to capture and exploit the relatedness between tasks. Based on real-world house transaction data collected in Melbourne, Australia. We design extensive experimental evaluations, and the results indicate a significant superiority of MTL-based methods over state-of-the-art approaches. Meanwhile, we conduct an in-depth analysis on the impact of task definitions and method selections in MTL on the prediction performance, and demonstrate that the impact of task definitions on prediction performance far exceeds that of method selections.

Learning a policy using only observational data is challenging because the distribution of states it induces at execution time may differ from the distribution observed during training. We propose to train a policy by unrolling a learned model of the environment dynamics over multiple time steps while explicitly penalizing two costs: the original cost the policy seeks to optimize, and an uncertainty cost which represents its divergence from the states it is trained on. We measure this second cost by using the uncertainty of the dynamics model about its own predictions, using recent ideas from uncertainty estimation for deep networks. We evaluate our approach using a large-scale observational dataset of driving behavior recorded from traffic cameras, and show that we are able to learn effective driving policies from purely observational data, with no environment interaction.

Building on a specific formalization of analogical relationships of the form "A relates to B as C relates to D", we establish a connection between two important subfields of artificial intelligence, namely analogical reasoning and kernel-based machine learning. More specifically, we show that so-called analogical proportions are closely connected to kernel functions on pairs of objects. Based on this result, we introduce the analogy kernel, which can be seen as a measure of how strongly four objects are in analogical relationship. As an application, we consider the problem of object ranking in the realm of preference learning, for which we develop a new method based on support vector machines trained with the analogy kernel. Our first experimental results for data sets from different domains (sports, education, tourism, etc.) are promising and suggest that our approach is competitive to state-of-the-art algorithms in terms of predictive accuracy.

Technology is critical for innovation, yet schools struggle to get students interested in this area. Could teaching robotics change this? The Queensland government has just announced plans to make teaching robotics compulsory in its new curriculum – aimed at students from prep through to year 10. Robotics matches the new digital technologies curriculum, strongly supported by the university sector and states, including Victoria. But while, worldwide, there are increasing initiatives such as the Robotics Academy in the US to teach robotics in schools, Australia isn't doing enough to get it taught in schools.